DeepSeek V4 Pro 0813 (on OpenRouter)

From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates

Understanding How DeepSeek's Flagship Open-Weight Models Evolved

Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index

Qwen 3. 8 27B scores 52 on the Artificial Analysis Intelligence Index That's the same score as GPT-5.

Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things

Friday's big release was Qwen 3. 8 27B , an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba's Qwen research lab.

Introducing Muse Glimmer

Introducing Muse Glimmer Meta are back in the open weights game! Muse Glimmer is a brand new 30B model under a clean Apache 2.

Joint Affine Spectral Shaping: Coupling Weight and Bias Updates Beyond Weight-Only Muon

arXiv:2608. 02991v1 Announce Type: new Abstract: Matrix spectral optimizers reshape weight-update spectra but usually delegate vector-valued biases to a separate optimizer.

llm-gemini 0.33

Release: llm-gemini 0. 33 It's been a while since the last llm-gemini release.

Kolmogorov--Arnold Networks for Small Language Models

arXiv:2607. 15525v1 Announce Type: cross Abstract: Kolmogorov--Arnold Networks (KANs) replace fixed node activations with learned one-dimensional edge functions, offering an explicit interface for interpretation and a possible alternative to transformer feed-forward networks.

SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization

arXiv:2608. 04084v1 Announce Type: new Abstract: Mixture-of-experts (MoE) networks pursue specialization through learned routers, gates, and load-balancing losses, yet at matched total-parameter budgets learned routers can underperform equal-weight No-Routing baselines.

Learned, Then Lost: A Measured Single-Example Counterfactual in Pre-training

The study measured the impact of a single training example on a GPT‑2 model by running 24 counterfactual experiments. 32 models were trained from scratch on OpenWebText, and at a specific training step a single batch row was replaced with a 194‑token passage under three conditions (fluent prose, fabricated subject, random characters) or left unchanged. Results showed that the passage was learned from one exposure and decayed, with measurable differences in cross‑entropy up to 50 steps after injection but no lasting effect at the final step.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget

arXiv:2608. 00916v1 Announce Type: cross Abstract: Modern reranking recipes---billion-scale cross-encoders, mixture-of-experts (MoE) backbones, and distillation against strong teachers---have outpaced the training infrastructure available to most academic groups.

An Embedded RISC-V Evaluation of Kolmogorov--Arnold Networks in Hard-Constrained Recurrent Physics-Informed Models

arXiv:2608. 00737v1 Announce Type: new Abstract: Hard-constrained recurrent physics-informed networks (HRPINNs) embed known dynamics inside a recurrent numerical integrator and restrict a neural branch to learning only the residual dynamics that the first-principles model does not capture.

Open-R1: a fully open reproduction of DeepSeek-R1